INDEX

Explanations

terms indicating something that has recently been established or formed

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulumi

-0.16

reach

-0.15

ewire

-0.14

lacak

-0.14

 eventual

-0.14

 Excell

-0.14

íħĶ

-0.14

ÐµÐ»Ð¸Ñĩ

-0.14

.lv

-0.14

ÐłÐ¾Ð·

-0.14

POSITIVE LOGITS

 mint

0.41

mint

0.31

wed

0.31

 Mint

0.26

 christ

0.22

 formed

0.22

wed

0.21

-open

0.20

-formed

0.19

 forming

0.19

Activations Density 0.012%

terms indicating something that has recently been established or formed

No Comments

No Known Activations

terms indicating something that has recently been established or formed

No Comments

No Known Activations